FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance
Paper • 2408.08189 • Published • 17
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("BirdL/FancyVideo", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Unoffical mirror of FancyVideo, requires SD-V1.5 or another other base model to be required seperately. Inference and training code is located at https://github.com/360CVGroup/FancyVideo
8/20/24: An offical repo has been created at huggingface.co/qihoo360/FancyVideo
@misc{feng2024fancyvideodynamicconsistentvideo, title={FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance}, author={Jiasong Feng and Ao Ma and Jing Wang and Bo Cheng and Xiaodan Liang and Dawei Leng and Yuhui Yin}, year={2024}, eprint={2408.08189}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2408.08189}, }
- Downloads last month
- -